Search Results for author:
Found 22 papers, 4 papers with code
Hufu: A Modality-Agnositc Watermarking System for Pre-Trained Transformers via Permutation Equivariance
The permutation equivariance ensures minimal interference between these two sets of model weights and thus high fidelity on downstream tasks.
FedReview: A Review Mechanism for Rejecting Poisoned Updates in Federated Learning
Federated learning has recently emerged as a decentralized approach to learn a high-performance model without access to user data.
Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
The reasoning performance of Large Language Models (LLMs) on a wide range of problems critically relies on chain-of-thought prompting, which involves providing a few chain of thought demonstrations as exemplars in prompts.
Language-Guided Diffusion Model for Visual Grounding
Specifically, we propose a language-guided diffusion framework for visual grounding, LG-DVG, which trains the model to progressively reason queried object boxes by denoising a set of noisy boxes with the language guide.
Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning
To address this problem, we develop a novel feature protection scheme against the reconstruction attack that effectively misleads the search to some pre-specified random values.
Pisces: Efficient Federated Learning via Guided Asynchronous Training
Current FL systems employ a participant selection strategy to select fast clients with quality data in each iteration.
OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks
This paper proposes a new eXplanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors.
Towards Private Learning on Decentralized Graphs with Local Differential Privacy
It is typical to collect these local views of social graphs and conduct graph learning tasks.
Multi-Modal Dynamic Graph Transformer for Visual Grounding
We found that existing VG methods are trapped by the single-stage grounding process that performs a sole evaluate-and- rank for meticulously prepared regions.
Towards Generalizable Personalized Federated Learning with Adaptive Local Adaptation
In this paper, we point out that this issue can be addressed by balancing information flow from the initial model and training dataset to the local adaptation.
PGD-2 can be better than FGSM + GradAlign
In this paper, we show that PGD-2 AT with random initialization (PGD-2-RS AT) and attack step size $\alpha=1. 25\epsilon/2$ only needs approximately a half computational cost of FGSM + GradAlign AT and actually can avoid catastrophic overfitting for large $\ell_\infty$ perturbations.
Interpreting Graph Neural Networks via Unrevealed Causal Learning
This paper proposes a new explanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors.
Generative Causal Explanations for Graph Neural Networks
Specifically, we formulate the problem of providing explanations for the decisions of GNNs as a causal learning task.
Context-aware deep model compression for edge cloud computing
While deep neural networks (DNNs) have led to a paradigm shift, its exorbitant computational requirement has always been a roadblock in its deployment to the edge, such as wearable devices and smartphones.
Ranked #169 on
Image Classification
on CIFAR-10
Towards Assessment of Randomized Smoothing Mechanisms for Certifying Adversarial Robustness
Based on our framework, we assess the Gaussian and Exponential mechanisms by comparing the magnitude of additive noise required by these mechanisms and the lower bounds (criteria).
Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition
We first formulate generation of adversarial skeleton actions as a constrained optimization problem by representing or approximating the physiological and physical constraints with mathematical formulations.
Learning-based Practical Smartphone Eavesdropping with Built-in Accelerometer
The second limitation comes from a common sense that these sensors can only pick up a narrow band (85-100Hz) of speech signals due to a sampling ceiling of 200Hz.
Shoestring: Graph-Based Semi-Supervised Learning with Severely Limited Labeled Data
More specifically, we address the problem of graph-based semi-supervised learning in the presence of severely limited labeled samples, and propose a new framework, called {\em Shoestring}, that improves the learning performance through semantic transfer from these very few labeled samples to large numbers of unlabeled samples.
A Unified framework for randomized smoothing based certified defenses
We answer the above two questions by first demonstrating that Gaussian mechanism and Exponential mechanism are the (near) optimal options to certify the $\ell_2$ and $\ell_\infty$-normed robustness.
Post: Device Placement with Cross-Entropy Minimization and Proximal Policy Optimization
It is critical to place operations in a neural network on these devices in an optimal way, so that the training process can complete within the shortest amount of time.
Spotlight: Optimizing Device Placement for Training Deep Neural Networks
Training deep neural networks (DNNs) requires an increasing amount of computation resources, and it becomes typical to use a mixture of GPU and CPU devices.
Semi-Dynamic Load Balancing: Efficient Distributed Learning in Non-Dedicated Environments
Efficient model training requires eliminating such stragglers, yet for modern ML workloads, existing load balancing strategies are inefficient and even infeasible.
